5 Papers Accepted by ICLR’23

The Eleventh International Conference on Learning Representations (ICLR 2023) just released its accepted paper list. BioGeometry and Mila team has 5 papers accepted by the conference. These papers cover areas such as protein design, protein-ligand docking, protein & molecular representation learning, and node classification on text-attributed graphs. Advanced techniques, including generative models, geometric pretraining, contrastive learning, and variational inference, are proposed or utilized. Congratulations to all our researchers and collaborators!

ProtSeed: Protein Sequence and Structure Co-Design with Equivariant Translation

Joint sequence-structure translation enables fast generative protein design.

ICLR 2023

E3Bind: An End-to-End Equivariant Network for Protein-Ligand Docking

End-to-end protein-ligand docking with SE(3)-equivariance.

ICLR 2023

GearNet: Protein Representation Learning by Geometric Structure Pretraining

Multiview contrastive pretraining yields rich protein structure representations.

ICLR 2023

SE(3)-DDM: Molecular Geometry Pretraining with SE(3)-Invariant Denoising Distance Matching

SE(3)-invariant 3D structure pretraining improves downstream performance.

ICLR 2023

GLEM: Learning on Large-scale Text-attributed Graphs via Variational Inference

GNN and LM fused as one with scalability & SOTA results on OGB datasets.

ICLR 2023 Notable Top 5%